AI Safety

What Machines See Is Not What They Get: Fooling Scene Text Recognition Models With Adversarial Text Images CVPR 2020 When NAS Meets Robustness: In Search of Robust Architectures Against Adversarial Attacks CVPR 2020 A Bayesian Approach to Robust Reinforcement Learning UAI 2019 A Dual Approach to Verify and Train Deep Networks IJCAI 2019 Adversarial Defense via Learning to Generate Diverse Attacks ICCV 2019 Adversarial Music: Real world Audio Adversary against Wake-word Detection System NeurIPS 2019 Adversarial Training and Robustness for Multiple Perturbations NeurIPS 2019 advPattern: Physical-World Attacks on Deep Person Re-Identification via Adversarially Transformable Patterns ICCV 2019 AI in Recruiting. Multi-agent Systems Architecture for Ethical and Legal Auditing IJCAI 2019 A Learnable Safety Measure CoRL 2019 A Little Is Enough: Circumventing Defenses For Distributed Learning NeurIPS 2019 Analyzing Federated Learning through an Adversarial Lens ICML 2019 Are adversarial examples inevitable? ICLR 2019 Ask not what AI can do, but what AI should do: Towards a framework of task delegability NeurIPS 2019 A Statistical Approach to Assessing Neural Network Robustness ICLR 2019 Attacking Optical Flow ICCV 2019 Attribution-Based Confidence Metric For Deep Neural Networks NeurIPS 2019 A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning NeurIPS 2019 Benchmarking Neural Network Robustness to Common Corruptions and Perturbations ICLR 2019 Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attacks ICCV 2019 Bit-Flip Attack: Crushing Neural Network With Progressive Bit Search ICCV 2019 Blameworthiness in Multi-Agent Settings AAAI 2019 Building Ethically Bounded AI AAAI 2019 Certified Adversarial Robustness for Deep Reinforcement Learning CoRL 2019 Certified Adversarial Robustness via Randomized Smoothing ICML 2019